INDEX

Explanations

code-related terms such as angular, import, module, component, and route

oai_token-act-pair · gemini-2.0-flash

angular

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atak

-0.51

 combineReducers

-0.50

 joaat

-0.49

IBOutlet

-0.49

 Silber

-0.49

dotenv

-0.48

apur

-0.47

’

-0.47

TagHelper

-0.47

 EdgeInsets

-0.47

POSITIVE LOGITS

 itſelf

0.54

 themſelves

0.49

 purpoſe

0.48

 ſeveral

0.48

 himſelf

0.46

 Cæsar

0.46

PerformLayout

0.46

 myſelf

0.46

 Majefty

0.46

 ")");

0.45

Activations Density 2.662%

code-related terms such as angular, import, module, component, and route

angular

No Comments

No Known Activations